{"total":414,"rows":[{"id":"2404.00456","title":"QuaRot: Outlier-Free 4-Bit Inference in Rotated LLMs","created":"2024-03-30","cited_by_count":634,"area":"inference"},{"id":"2407.08608","title":"FlashAttention-3: Fast and Accurate Attention with Asynchrony and Low-precision","created":"2024-07-11","cited_by_count":519,"area":null},{"id":"2405.16406","title":"SpinQuant: LLM quantization with learned rotations","created":"2024-05-26","cited_by_count":471,"area":"inference"},{"id":"2308.13137","title":"OmniQuant: Omnidirectionally Calibrated Quantization for Large Language Models","created":"2023-08-25","cited_by_count":424,"area":null},{"id":"2402.04396","title":"QuIP#: Even Better LLM Quantization with Hadamard Incoherence and Lattice Codebooks","created":"2024-02-06","cited_by_count":378,"area":null},{"id":"2402.17764","title":"The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits","created":"2024-02-27","cited_by_count":308,"area":null},{"id":"2308.07633","title":"A Survey on Model Compression for Large Language Models","created":"2023-08-15","cited_by_count":269,"area":null},{"id":"2405.04532","title":"QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving","created":"2024-05-07","cited_by_count":208,"area":"inference"},{"id":"2404.14294","title":"A Survey on Efficient Inference for Large Language Models","created":"2024-04-22","cited_by_count":205,"area":"inference"},{"id":"2310.11453","title":"BitNet: Scaling 1-bit Transformers for Large Language Models","created":"2023-10-17","cited_by_count":189,"area":null},{"id":"2312.03863","title":"Efficient Large Language Models: A Survey","created":"2023-12-06","cited_by_count":186,"area":null},{"id":"2406.01721","title":"DuQuant: Distributing Outliers via Dual Transformation Makes Stronger Quantized LLMs","created":"2024-06-03","cited_by_count":167,"area":null},{"id":"2402.16363","title":"LLM Inference Unveiled: Survey and Roofline Model Insights","created":"2024-02-26","cited_by_count":152,"area":"inference"},{"id":"2402.04291","title":"BiLLM: Pushing the Limit of Post-Training Quantization for LLMs","created":"2024-02-06","cited_by_count":144,"area":null},{"id":"2410.09426","title":"FlatQuant: Flatness Matters for LLM Quantization","created":"2024-10-12","cited_by_count":131,"area":null},{"id":"2407.11062","title":"EfficientQAT: Efficient Quantization-Aware Training for Large Language Models","created":"2024-07-10","cited_by_count":127,"area":null},{"id":"2504.19874","title":"TurboQuant: Online Vector Quantization with Near-optimal Distortion Rate","created":"2025-04-28","cited_by_count":125,"area":null},{"id":"2411.02359","title":"DeeR-VLA: Dynamic Inference of Multimodal Large Language Models for Efficient Robot Execution","created":"2024-11-04","cited_by_count":117,"area":"lr"},{"id":"2406.02540","title":"ViDiT-Q: Efficient and Accurate Quantization of Diffusion Transformers for Image and Video Generation","created":"2024-06-04","cited_by_count":115,"area":"diffusion"},{"id":"2406.06282","title":"PowerInfer-2: Fast Large Language Model Inference on a Smartphone","created":"2024-06-10","cited_by_count":103,"area":null},{"id":"2501.13987","title":"OstQuant: Refining Large Language Model Quantization with Orthogonal and Scaling Transformations for Better Distribution Fitting","created":"2025-01-23","cited_by_count":97,"area":null},{"id":"2411.04330","title":"Scaling Laws for Precision","created":"2024-11-07","cited_by_count":95,"area":null},{"id":"2310.04564","title":"ReLU Strikes Back: Exploiting Activation Sparsity in Large Language Models","created":"2023-10-06","cited_by_count":94,"area":null},{"id":"2406.11235","title":"QTIP: Quantization with Trellises and Incoherence Processing","created":"2024-06-17","cited_by_count":91,"area":null},{"id":"2401.08092","title":"A Survey of Resource-efficient LLM and Multimodal Foundation Models","created":"2024-01-16","cited_by_count":86,"area":null},{"id":"2502.08773","title":"Universal Model Routing for Efficient LLM Inference","created":"2025-02-12","cited_by_count":86,"area":"inference"},{"id":"2402.10631","title":"BitDistiller: Unleashing the Potential of Sub-4-Bit LLMs via Self-Distillation","created":"2024-02-16","cited_by_count":84,"area":"distill"},{"id":"2310.00034","title":"PB-LLM: Partially Binarized Large Language Models","created":"2023-09-29","cited_by_count":83,"area":null},{"id":"2308.14352","title":"EdgeMoE: Empowering Sparse Large Language Models on Mobile Devices","created":"2023-08-28","cited_by_count":69,"area":"moe"},{"id":"2402.12065","title":"WKVQuant: Quantizing Weight and Key/Value Cache for Large Language Models Gains More","created":"2024-02-19","cited_by_count":69,"area":null},{"id":"2310.08041","title":"QLLM: Accurate and Efficient Low-Bitwidth Quantization for Large Language Models","created":"2023-10-12","cited_by_count":64,"area":null},{"id":"2402.09748","title":"Model Compression and Efficient Inference for Large Language Models: A Survey","created":"2024-02-15","cited_by_count":64,"area":null},{"id":"2404.14047","title":"An empirical study of LLaMA3 quantization: from LLMs to MLLMs","created":"2024-04-22","cited_by_count":64,"area":"mllm"},{"id":"2405.14917","title":"SliM-LLM: Salience-Driven Mixed-Precision Quantization for Large Language Models","created":"2024-05-23","cited_by_count":63,"area":null},{"id":"2405.14852","title":"PV-Tuning: Beyond Straight-Through Estimation for Extreme LLM Compression","created":"2024-05-23","cited_by_count":61,"area":null},{"id":"2504.02692","title":"GPTAQ: Efficient Finetuning-Free Quantization for Asymmetric Calibration","created":"2025-04-03","cited_by_count":60,"area":null},{"id":"2405.18886","title":"Compressing Large Language Models using Low Rank and Low Precision Decomposition","created":"2024-05-29","cited_by_count":59,"area":null},{"id":"2403.15447","title":"Decoding Compressed Trust: Scrutinizing the Trustworthiness of Efficient LLMs Under Compression","created":"2024-03-18","cited_by_count":57,"area":null},{"id":"2409.17066","title":"VPTQ: Extreme Low-bit Vector Post-Training Quantization for Large Language Models","created":"2024-09-25","cited_by_count":57,"area":null},{"id":"2402.10517","title":"Any-Precision LLM: Low-Cost Deployment of Multiple, Different-Sized LLMs","created":"2024-02-16","cited_by_count":54,"area":null},{"id":"2408.11743","title":"MARLIN: Mixed-Precision Auto-Regressive Parallel Inference on Large Language Models","created":"2024-08-21","cited_by_count":52,"area":null},{"id":"2411.07191","title":"The Super Weight in Large Language Models","created":"2024-11-11","cited_by_count":52,"area":null},{"id":"2501.16383","title":"RotateKV: Accurate and Robust 2-Bit KV Cache Quantization for LLMs via Outlier-Aware Adaptive Rotations","created":"2025-01-25","cited_by_count":46,"area":"inference"},{"id":"2502.02631","title":"ParetoQ: Improving Scaling Laws in Extremely Low-bit LLM Quantization","created":"2025-02-04","cited_by_count":46,"area":null},{"id":"2412.19509","title":"MBQ: Modality-Balanced Quantization for Large Vision-Language Models","created":"2024-12-27","cited_by_count":45,"area":"mllm"},{"id":"2406.06385","title":"Low-Rank Quantization-Aware Training for LLMs","created":"2024-06-10","cited_by_count":43,"area":null},{"id":"2310.16795","title":"QMoE: Practical Sub-1-Bit Compression of Trillion-Parameter Models","created":"2023-10-25","cited_by_count":42,"area":"moe"},{"id":"2402.02446","title":"LQER: Low-Rank Quantization Error Reconstruction for LLMs","created":"2024-02-04","cited_by_count":41,"area":null},{"id":"2504.09629","title":"Quantization Error Propagation: Revisiting Layer-Wise Post-Training Quantization","created":"2025-04-13","cited_by_count":41,"area":null},{"id":"2402.10193","title":"BitDelta: Your Fine-Tune May Only Be Worth One Bit","created":"2024-02-15","cited_by_count":39,"area":null},{"id":"2505.14669","title":"Quartet: Native FP4 Training Can Be Optimal for Large Language Models","created":"2025-05-20","cited_by_count":39,"area":null},{"id":"2310.18859","title":"SiDA-MoE: Sparsity-Inspired Data-Aware Serving for Efficient and Scalable Large Mixture-of-Experts Models","created":"2023-10-29","cited_by_count":38,"area":"moe"},{"id":"2411.02530","title":"A Comprehensive Study on Quantization Techniques for Large Language Models","created":"2024-10-30","cited_by_count":36,"area":null},{"id":"2412.14363","title":"ResQ: Mixed-Precision Quantization of Large Language Models with Low-Rank Residuals","created":"2024-12-18","cited_by_count":36,"area":null},{"id":"2312.07950","title":"CBQ: Cross-Block Quantization for Large Language Models","created":"2023-12-13","cited_by_count":34,"area":null},{"id":"2312.15159","title":"Understanding the Potential of FPGA-Based Spatial Acceleration for Large Language Model Inference","created":"2023-12-23","cited_by_count":33,"area":null},{"id":"2505.07004","title":"GuidedQuant: Large Language Model Quantization via Exploiting End Loss Guidance","created":"2025-05-11","cited_by_count":32,"area":null},{"id":"2509.23202","title":"Bridging the Gap Between Promise and Performance for Microscaling FP4 Quantization","created":"2025-09-27","cited_by_count":32,"area":null},{"id":"2403.12422","title":"Jetfire: Efficient and Accurate Transformer Pretraining with INT8 Data Flow and Per-Block Quantization","created":"2024-03-19","cited_by_count":31,"area":null},{"id":"2408.01803","title":"STBLLM: Breaking the 1-Bit Barrier with Structured Binary LLMs","created":"2024-08-03","cited_by_count":31,"area":null},{"id":"2409.16694","title":"A Survey of Low-bit Large Language Models: Basics, Systems, and Algorithms","created":"2024-09-25","cited_by_count":31,"area":null},{"id":"2406.05981","title":"ShiftAddLLM: Accelerating Pretrained LLMs via Post-Training Multiplication-Less Reparameterization","created":"2024-06-10","cited_by_count":30,"area":null},{"id":"2501.13484","title":"MambaQuant: Quantizing the Mamba Family with Variance Aligned Rotation Methods","created":"2025-01-23","cited_by_count":29,"area":"ssm"},{"id":"2406.00800","title":"MagR: Weight Magnitude Reduction for Enhancing Post-Training Quantization","created":"2024-06-02","cited_by_count":28,"area":null},{"id":"2406.02913","title":"Zeroth-Order Fine-Tuning of LLMs with Extreme Sparsity","created":"2024-06-05","cited_by_count":28,"area":null},{"id":"2505.11695","title":"Qronos: Correcting the Past by Shaping the Future... in Post-Training Quantization","created":"2025-05-16","cited_by_count":28,"area":null},{"id":"2405.18218","title":"FinerCut: Finer-grained Interpretable Layer Pruning for Large Language Models","created":"2024-05-28","cited_by_count":27,"area":null},{"id":"2502.10424","title":"QuantSpec: Self-Speculative Decoding with Hierarchical Quantized KV Cache","created":"2025-02-05","cited_by_count":27,"area":"inference"},{"id":"2309.14021","title":"LORD: Low Rank Decomposition Of Monolingual Code LLMs For One-Shot Compression","created":"2023-09-25","cited_by_count":26,"area":null},{"id":"2407.18158","title":"Unlocking Tokens as Data Points for Generalization Bounds on Larger Language Models","created":"2024-07-25","cited_by_count":25,"area":null},{"id":"2405.17849","title":"I-LLM: Efficient Integer-Only Inference for Fully-Quantized Low-Bit Large Language Models","created":"2024-05-28","cited_by_count":23,"area":null},{"id":"2410.07265","title":"A Survey: Collaborative Hardware and Software Design in the Era of Large Language Models","created":"2024-10-08","cited_by_count":23,"area":null},{"id":"2502.09720","title":"NestQuant: Nested Lattice Quantization for Matrix Products and LLMs","created":"2025-02-13","cited_by_count":23,"area":null},{"id":"2505.22988","title":"Model-Preserving Adaptive Rounding","created":"2025-05-29","cited_by_count":23,"area":null},{"id":"2508.14896","title":"Quantization Meets dLLMs: A Systematic Study of Post-training Quantization for Diffusion LLMs","created":"2025-08-20","cited_by_count":23,"area":null},{"id":"2407.10032","title":"LeanQuant: Accurate and Scalable Large Language Model Quantization with Loss-error-aware Grid","created":"2024-07-14","cited_by_count":22,"area":null},{"id":"2408.08554","title":"ABQ-LLM: Arbitrary-Bit Quantized Inference Acceleration for Large Language Models","created":"2024-08-16","cited_by_count":22,"area":"inference"},{"id":"2410.06040","title":"QERA: an Analytical Framework for Quantization Error Reconstruction","created":"2024-10-08","cited_by_count":22,"area":null},{"id":"2502.05003","title":"QuEST: Stable Training of LLMs with 1-Bit Weights and Activations","created":"2025-02-07","cited_by_count":22,"area":null},{"id":"2502.11880","title":"Bitnet.cpp: Efficient Edge Inference for Ternary LLMs","created":"2025-02-17","cited_by_count":22,"area":null},{"id":"2405.14428","title":"Mitigating Quantization Errors Due to Activation Spikes in GLU-Based LLMs","created":"2024-05-23","cited_by_count":21,"area":null},{"id":"2410.17770","title":"Small Singular Values Matter: A Random Matrix Analysis of Transformer Models","created":"2024-10-23","cited_by_count":21,"area":null},{"id":"2411.17525","title":"Pushing the Limits of Large Language Model Quantization via the Linearity Theorem","created":"2024-11-26","cited_by_count":21,"area":null},{"id":"2504.19449","title":"R-Sparse: Rank-Aware Activation Sparsity for Efficient LLM Inference","created":"2025-04-28","cited_by_count":21,"area":"inference"},{"id":"2507.18553","title":"The Geometry of LLM Quantization: GPTQ as Babai's Nearest Plane Algorithm","created":"2025-07-24","cited_by_count":20,"area":null},{"id":"2511.04214","title":"Block Rotation is All You Need for MXFP4 Quantization","created":"2025-11-06","cited_by_count":20,"area":null},{"id":"2506.17188","title":"Towards AI Search Paradigm","created":"2025-06-20","cited_by_count":19,"area":null},{"id":"2403.06082","title":"FrameQuant: Flexible Low-Bit Quantization for Transformers","created":"2024-03-10","cited_by_count":18,"area":null},{"id":"2404.01012","title":"Query Performance Prediction using Relevance Judgments Generated by Large Language Models","created":"2024-04-01","cited_by_count":18,"area":null},{"id":"2405.03103","title":"Learning from Students: Applying t-Distributions to Explore Accurate and Efficient Formats for LLMs","created":"2024-05-06","cited_by_count":18,"area":null},{"id":"2408.06003","title":"LUT Tensor Core: A Software-Hardware Co-Design for LUT-Based Low-Bit LLM Inference","created":"2024-08-12","cited_by_count":18,"area":null},{"id":"2411.11745","title":"BitMoD: Bit-serial Mixture-of-Datatype LLM Acceleration","created":"2024-11-18","cited_by_count":18,"area":null},{"id":"2502.15799","title":"Investigating the Impact of Quantization Methods on the Safety and Reliability of Large Language Models","created":"2025-02-18","cited_by_count":18,"area":"lr"},{"id":"2406.07177","title":"TernaryLLM: Ternarized Large Language Model","created":"2024-06-11","cited_by_count":17,"area":null},{"id":"2509.21302","title":"Quantized Visual Geometry Grounded Transformer","created":"2025-09-25","cited_by_count":17,"area":null},{"id":"2511.04063","title":"DartQuant: Efficient Rotational Distribution Calibration for LLM Quantization","created":"2025-11-06","cited_by_count":17,"area":null},{"id":"2511.10645","title":"ParoQuant: Pairwise Rotation Quantization for Efficient Reasoning LLM Inference","created":"2025-11-13","cited_by_count":17,"area":"lr"},{"id":"2406.09904","title":"QQQ: Quality Quattuor-Bit Quantization for Large Language Models","created":"2024-06-14","cited_by_count":16,"area":null},{"id":"2412.14590","title":"MixLLM: LLM Quantization with Global Mixed-precision between Output-features and Highly-efficient System Design","created":"2024-12-19","cited_by_count":16,"area":null},{"id":"2506.04985","title":"FPTQuant: Function-Preserving Transforms for LLM Quantization","created":"2025-06-05","cited_by_count":16,"area":null}],"next_cursor":"100"}